OpenAI's legacy image generation model supporting generations, edits with masks (inpainting), and variations
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
DALL-E 2
#59 of 62 in Text-to-Image
FLUX.1 [schnell]
#48 of 62 in Text-to-Image
Where the votes landed
DALL-E 2
0%
win rate
Ties
0%
FLUX.1 [schnell]
0%
win rate
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
AI Judge Analysis
DALL-E 2
- + Features a wooden table with realistic reflections.
- + Attempts a soft lighting style.
- − Failed to include a red book.
- − Failed to include a blue sphere inside the cube (the cube itself appears to have a red core).
- − The 'green plant' is replaced by a massive blue blurry object.
- − Low image resolution and poor clarity.
FLUX.1 [schnell]
- + Excellent prompt adherence, including the blue sphere inside the cube and the red book on top.
- + High visual quality with sharp textures on the leaves and wooden table.
- + Accurately renders the plant behind the glass with realistic distortion.
- + Followed lighting instructions perfectly with soft light coming from the left window.
- − Includes an extra blue sphere on top of the book that was not requested.
- − The sphere inside the cube appears to be floating without a visible stand.
Verdict: DALL-E 2 failed significantly on prompt adherence, missing almost all requested spatial relationships and objects. FLUX.1 [schnell] followed the prompt accurately, producing a high-fidelity image with clear compositions, although it added one extra object not found in the text.
Candid Street Photography
Text-to-Image“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
AI Judge Analysis
DALL-E 2
- + Successfully captures an 'imperfect framing' look with objects in the foreground
- + Good interpretation of shallow depth of field
- − Fails to show the subject's face or clear 'elderly Japanese man' features
- − Image is too abstract and lacks the requested motion blur and realistic detail
FLUX.1 [schnell]
- + Excellent adherence to the 'elderly Japanese man' and 'red bicycle' prompts
- + Very high visual quality with realistic skin textures and atmospheric light reflections
- + Cinematic composition with clear bokeh and wet pavement
- − Missing the 'motion blur from passing cars' as the cars appear static
- − Framing is quite standard and lacks the 'imperfect' feel requested
Verdict: FLUX.1 [schnell] produced a high-quality, clear image that followed the majority of the prompt instructions, including the subject description and lighting. DALL-E 2 produced an abstract, out-of-focus shot that failed to clearly depict the requested subject or the realism required, though it did attempt the 'imperfect framing'.
Fantasy Warrior
Text-to-Image“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
AI Judge Analysis
DALL-E 2
- + Captures a strong sense of texture and gritty battle-worn appearance
- + Effectively shows bokeh light in the background
- − Extreme lack of anatomical coherence and clarity
- − Fails to show life-like eyes, hair braids, or a recognizable face
- − Overly blurry and looks more like a weathered statue than a person
FLUX.1 [schnell]
- + Excellent adherence to all prompt details including braids with beads, scars, and ornate armor
- + Stunningly lifelike eyes and skin texture
- + Strong composition with effective warm lighting and shallow depth of field
- − The 'dirt' on the skin is very subtle, bordering on clean-shaven
- − Hair braids blend slightly into the background elements
Verdict: FLUX.1 [schnell] is the clear winner, meticulously following every aspect of the prompt from the braided hair with beads to the ornate engraving on the armor. In contrast, DALL-E 2 produced an abstract, incoherent image that failed to capture any of the specific facial or anatomical requirements.
Modern Clean Menu
Text-to-Image“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
AI Judge Analysis
DALL-E 2
- + Features a bold, impactful sans-serif aesthetic.
- + Vibrant colors that feel energetic.
- − Layout is chaotic and does not resemble a functional menu.
- − Food photos are abstract, fragmented, and unappetizing.
- − Text is completely illegible and lacks actual menu sections.
FLUX.1 [schnell]
- + Excellent adherence to the grid layout and menu sections requested.
- + Clean, professional typography that mimics a real casual dining menu.
- + Food images are recognizable and well-placed within the design.
- − Small body text is still somewhat garbled upon close inspection.
- − The 'ORFEFUS' section title is nonsensical.
Verdict: FLUX.1 [schnell] followed the prompt accurately, producing a functional and aesthetically pleasing menu layout with clear sections for pizza and mains. In contrast, DALL-E 2 produced a fragmented, abstract image that fails to resemble a professional menu or display coherent food items.
Magic Burger Explosion: Fiery Photorealism Challenge
Text-to-Image“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
AI Judge Analysis
DALL-E 2
- + Strong fiery atmosphere and glowing effect
- + Dynamic interpretation of the "exploded" concept
- − Failed significantly on text rendering with gibberish words
- − Low photorealism with blurry, painterly textures
- − Missing required secondary text and price
FLUX.1 [schnell]
- + High resolution and photorealistic textures on the burger
- + Excellent adherence to text instructions including 'LIMITED TIME ONLY'
- + Accurately represents the fiery background with glowing embers
- − The burger itself is not fully 'exploded' into components, though snacks/croutons are floating
- − Slight typo in 'MAGIC' (rendered as 'AGIC') and redundant price in the starburst
Verdict: FLUX.1 [schnell] is the clear winner as it successfully rendered most of the requested text and maintains a high level of photorealistic detail. DALL-E 2 produced an abstract, blurry image with illegible text that did not meet the professional advertisement criteria.
Chalkboard Menu
Text-to-Image“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
AI Judge Analysis
DALL-E 2
- + Features a thick, textured chalk aesthetic
- − Text is completely illegible gibberish
- − Fails to follow specific menu item instructions
- − Poor resolution and heavy artifacts
FLUX.1 [schnell]
- + Follows the date and menu item instructions with reasonable accuracy
- + High resolution image with a clear café background
- + Text exhibits natural handwriting variations as requested
- − Several spelling errors like 'Octtoopus' and 'Lemors'
- − The chalk texture is very clean, appearing more like a chalk marker than traditional dusty chalk
- − Missing the 'A' in 'April'
Verdict: FLUX.1 [schnell] is the clear winner as it successfully renders the requested text and maintains a coherent café environment, despite a few minor spelling errors. DALL-E 2 fails the prompt entirely, producing illegible textures and random characters that do not resemble the requested menu items.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
AI Judge Analysis
DALL-E 2
- + Features a coherent, painterly style that fits a 'surreal' request.
- + Accurately places the scene in a space environment.
- − Completely failed the prompt logic of having the horse on top of the astronaut.
- − Low resolution with significant noise and muddy textures.
- − Anatomical issues with the horse's legs and the astronaut's scale.
FLUX.1 [schnell]
- + Followed the difficult logical inversion of having the horse on top of the astronaut.
- + High visual quality with sharp details and cinematic lighting.
- + Creative interpretation where the horse is saddled onto the astronaut's pack.
- − The horse features two heads, which is an unintended anatomical artifact.
- − The orientation of the astronaut is slightly confusing in relation to the 'top' horse.
Verdict: DALL-E 2 provided a generic interpretation of the prompt, failing to follow the specific instruction for the horse to be on top. FLUX.1 [schnell] successfully followed the complex instruction and produced a much higher quality, cinematic image, despite the minor artifact of a double-headed horse.
The Capybara Taxi Driver
Text-to-Image“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
AI Judge Analysis
DALL-E 2
- + Attempts to show the capybara in the driver's seat and a passenger.
- − Extremely poor visual quality with severe anatomical glitches.
- − The human appears to be in the front seat or merged with the driving position.
- − Fails almost every descriptive detail of the prompt, including the cap and the bored expression.
FLUX.1 [schnell]
- + Excellent adherence to all prompt details including the cap, jacket, and bored expression.
- + High-quality photorealistic rendering with realistic lighting and textures.
- + Clear composition that distinguishes the driver and the passenger as requested.
- − The word 'TAXI' on the cap is slightly off-center.
- − The capybara's right paw is not fully gripping the steering wheel.
Verdict: FLUX.1 [schnell] followed the prompt almost perfectly, delivering a high-quality, coherent image that looks professional and cinematic. DALL-E 2 struggled significantly, producing a distorted image with nightmarish artifacts and failing to separate the characters correctly.
The Halloween Invitation
Text-to-Image“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”
AI Judge Analysis
DALL-E 2
- + Strong vintage parchment texture and aesthetic
- + Atmospheric and spooky border design
- − Text is largely unintelligible gibberish
- − Fails to include several specific prompt elements like the jack-o-lantern
- − Low visual clarity and lacks the requested polished, cinematic lighting
FLUX.1 [schnell]
- + Successfully includes almost all requested elements including bats, trees, and jack-o-lantern
- + High resolution with clean, professional graphic design
- + Text is legible despite some minor spelling errors
- − Repetitive and redundant text fields at the bottom
- − Includes typos such as 'firiichts' and 'butistigtion'
- − The flat vector-style illustration lacks a truly 'vintage parchment' feel
Verdict: FLUX.1 [schnell] is the superior model here as it accurately follows the complex prompt requirements, including the specific date and location. While DALL-E 2 captures a better 'vintage' texture, it fails completely on text legibility and object inclusion, whereas FLUX.1 [schnell] creates a functional, albeit slightly flawed, invitation layout.
Isometric Miniature Diorama Scenes
Text-to-Image“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
AI Judge Analysis
DALL-E 2
- + Attempts to place text within the 3D space with shadows.
- + Clean isometric angle for the base plate.
- − Failed to render the word 'JAPAN' and misspelled 'SUSHI' as 'Sush'.
- − The 'sushi' is abstract and poorly rendered, lacking clear textures.
- − Strong shadows and high contrast clash with the requested soft, gentle lighting.
FLUX.1 [schnell]
- + Perfect adherence to text and icon requirements.
- + High-quality textures on the sushi piece, showing rice grains and salmon marbling.
- + Clean, professional 3D diorama aesthetic with soft lighting and a light blue background.
- − Missed the word 'SUSHI' below the word 'JAPAN' (only 'JAPAN' is present).
- − Composition is a bit vertically stretched compared to a tighter square crop.
Verdict: FLUX.1 [schnell] follows the prompt's stylistic instructions much more effectively, producing a high-quality 3D diorama with realistic textures and correct text. DALL-E 2 fails significantly on the text rendering and the actual representation of the sushi, resulting in an abstract and confusing image.
Adorable Baby Animals in Sunny Meadow
Text-to-Image“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
AI Judge Analysis
DALL-E 2
- + Includes butterflies and a wide field of grass.
- − Significant anatomical distortion in the animals and butterflies.
- − Poor visual quality with blurry textures and artifacts.
- − The fox and bunny are unrecognizable or poorly rendered blobs.
FLUX.1 [schnell]
- + Excellent photorealistic texture on the fur and flowers.
- + Accurately represents all requested animals (puppy, kitten, bunny, fox).
- + Beautiful lighting and bokeh effect that matches the sunrise request.
- − The bunny has somewhat feline facial features.
- − The composition is a bit crowded with all animals packed together.
Verdict: FLUX.1 [schnell] is far superior, delivering high-resolution, photorealistic textures and coherent animal anatomy that matches the magical, wholesome prompt. DALL-E 2 fails significantly on technical quality, producing distorted animals and severe visual artifacts throughout the scene.
Vintage Cafe Logo
Text-to-Image“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
AI Judge Analysis
DALL-E 2
- + Successfully captures the requested steam icon above the dome.
- + Follows the warm brown and cream color palette correctly.
- + Provides a minimalist, vector-style aesthetic.
- − The text is completely garbled and unintelligible.
- − Fails to include the 'Est. 1720' banner requested in the prompt.
- − The 'textured' effect looks like low-resolution artifacting rather than a deliberate style.
FLUX.1 [schnell]
- + Excellent layout with a professional circular emblem and banner composition.
- + Typography is clean, classic, and highly legible.
- + High visual quality with sharp lines and appropriate vector styling.
- − Spells the brand name incorrectly as 'Cafe Framilan' and the date as '7720'.
- − Missed the specific 'steam' element requested in the prompt.
- − The cloche looks slightly more like a building dome than a food cover.
Verdict: DALL-E 2 followed the technical icon requirements like steam better, but the output is unusable due to severe text corruption. FLUX.1 [schnell] produced a much more professional and aesthetically pleasing logo with superior composition, despite minor spelling errors and a typo in the establishment date.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
AI Judge Analysis
DALL-E 2
- + Adheres well to the navy and red color palette
- + Captures an 'abstract data' aesthetic that feels technical
- − Text is nonsensical and includes a bizarre primary header ('ALLPOO')
- − The layout is cluttered and fails to present a clear 6-step chronological infographic
- − Iconography is messy and unrecognizable
FLUX.1 [schnell]
- + Excellent clean, flat-vector style with professional composition
- + Features recognizable icons including planets, orbits, and a landing module
- + Clearly organized layout that attempts to follow the requested steps
- − The rocket graphic at the top is oddly duplicated/mirrored and doesn't look like a Saturn V
- − Small body text is still mostly gibberish, though headings like 'LANDING' are correct
Verdict: FLUX.1 [schnell] is the clear winner as it produces a professional, clean infographic layout that actually follows the flat-vector style and logical sequence requested. DALL-E 2 fails significantly on legibility, producing nonsensical and humorous text errors like 'ALLPOO' and a cluttered, confusing composition.
Explore each model
Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps